differences in movements of families through the income-to-needs distribution, per- haps also stemming from policy differences.
We first take a crude approach to eliminating the spurious influence of the business cycle on the estimates. In particular, the years in our sample in which the federal mini-
mum wage was raised coincided with the recession in the early 1990s and thus with rel- atively sharp increases in state unemployment rates. As it seems unlikely that the federal
minimum-wage increases actually caused the recession, we also present estimates in which we exclude the years influenced by a federal minimum-wage increase 1990 and
1991 as well as 1992, in which the lagged increase from 1991 occurred. This restric- tion avoids confounding the influence of the recession with minimum-wage effects,
although it also likely goes too far in eliminating useful variation in the data.
An alternative and more informative approach is to mimic a regression model that includes fixed year and state effects. To do this, we first estimate the median propor-
tional change in income-to-needs by state across all years. We then adjust each fam- ily’s income-to-needs in Year 2 so that this common state change is taken out of the
change in the family’s income-to-needs from Year 1 to Year 2. We make a parallel adjustment for the median proportional change by year across all states.
6
The dif- ference between the adjusted data on income-to-needs for each family in Year 2 and
Year 1 is the deviation around the average state change over all years in the sample and the average year change over all states in the sample. We then perform the basic
difference-in-difference analysis described above using these adjusted data.
D. State versus Federal Increases and Biases from Migration
A third potential bias in our estimates relates to the possibility of migration. Because we rely partly on state minimum-wage increases to identify the effects of minimum
wages and because changes in state minimum wages may influence the decision by workers and firms to move into or out of a state, the effects identified from state min-
imum-wage increases may differ from the effects of federal increases. As an example, Cushing 2003 finds that poor families tend to migrate into a state in response to min-
imum-wage increases. The magnitude of the migration response is modest, especially relative to the nonmigratory population, suggesting that it probably has only a small
impact on our estimates. Moreover, any effect will be muted considerably in our data because migrants are not in the matched CPS data; thus, we would only detect the
indirect effects of migration on those who already resided in the state.
Nonetheless, the presence of migration will lead our estimates to overstate the adverse impact of a federal minimum-wage increase in response to which migration
cannot really occur. In particular, if poor families migrate into a state that has Neumark, Schweitzer, and Wascher
875
6. We use the proportional change because the first difference of the level of income-to-needs is unlikely to apply very well to either tail of the distribution. In addition, using the proportional change controls for the
possibility that income-to-needs distributions shift because of changes in the price of skill that affect incomes multiplicatively. In particular, changes in the price of skill that are common across all states would “hollow
out” the lefthand tail of the distribution relatively more in higher-wage, higher-income states, which would bias our estimated minimum-wage effects to the extent that minimum-wage increases in higher-wage,
higher-income states provide relatively more or less identifying information. Because we use proportional changes, we estimate state-specific and year-specific medians rather than means to avoid outliers caused by
very high or low income-to-needs values for either of the two observations on a family.
recently raised its minimum wage, then poor families already in the state may face slightly more labor market competition, while poor families remaining behind in
other states may face slightly less, thereby worsening outcomes in the treatment group and improving them in the control group.
7
On the other hand, since the last federal minimum-wage increases in the mid-1990s, all of the changes in minimum wages in
the United States have been at the state level. For these increases, our method likely understates again, only slightly the effects of the minimum wage because our sam-
ple includes some federal variation.
IV. Results
